… Abstract—The increasing complexity of deep neural networks … To address this challenge,
split federated learning (SFL) has … to network resources and highlights the adaptability of client-…

… The implementation of these topologies in a virtual environment made it possible to simulate
diverse federated learning contexts and network configurations, testing the adaptability and …

… Abstract—This paper studies federated learning (FL) in a classic wireless network, where
learning clients share a common wireless link to a coordinating server to perform federated …

… Variants of Centralized Federated Learning The network variants and extensions of CFL
are designed to address the above challenges and adapt to different real-world application …

… , and network structure adaptability arose. To address these concerns, we propose a
platform using federated learning and private blockchain technology within a fog-IoT network. …

… networks have similarities with each other but other networks do not. We propose
Segmented-Federated Learning … evaluation and network segmentation, we aim to bring similar …

… In this paragraph, we evaluate the power consumption of the proposed federated learning
strategy. We consider two sources of power consumption for each device: local computation …

… machine learning method known as federated learning (FL) … , facilitating collaborative machine
learning training of complex … additional network traffic, its benefits in terms of adaptability …

… a convolutional neural network (CNN) with two layers, on CIFAR-10 and CIFAR-100, we
consider a three-layer CNN1, and on eICU We build a fully-connected network with two layers, …

… c) Well-studied channel models for FL networks a) Fixed deployment and low adaptability
to network dynamics and user distributions. b) Fixed service coverage, ie, not able to provide …